Code Security Reinvented: Navigating the era of AI
summary
GitHub Security Lab reports 1,000+ OSS security issues (600+ CVEs) with a 96% fix rate and shows practical demos using GitHub Copilot to convert vulnerable string concatenation into parameterized statements plus a regex guard; 60% of GitHub commits were AI-generated in 2023. Live features include co-pilot autofix that generates PRs to fix alerts, secret scanning that found ~30,000 offline secrets, static analysis via CodeQL, and fuzzing harness generation; a browser-playable training game speeds developer upskilling.
AI-written summary · about
chapters (14)
- 0:00Introduction and speaker intro
- 2:36AI in modern software development
- 5:47Writing safer code with AI
- 9:45AI pair programmer limitations
- 13:38AI for secrets detection
- 15:00Static application security testing
- 17:25Copilot autofix for vulnerabilities
- 21:02AI-assisted CodeQL queries
- 24:33AI for security guidance
- 27:23AI in fuzzing and automation
- 29:09Privacy and AI tools
- 30:34Developer time savings with AI
- 33:03Summary and future opportunities
- 36:19Closing and Q&A
related talks
32mCode Security Reinvented: Navigating the Era of AI
41mCode Security Reinvented Navigating the era of AI
58mSecuring Code in the Age of AI
30mHuman vs AI: How to Ship Secure Code
52mSecurity as Code: A DevSecOps Approach
23mCode Security Reinvented Navigating the era of AI
01h 02mHow AI is impacting cybersecurity. Does it?
26mSmarter Code, Sneakier Risks: Supply Chain Security in the Age of AI